Selenium Mcp

by amandeep-sg

3 stars

365 downloads

Not rated

GitHub

About

MCP tools build using selenium to automate web testing or scraping

Details

Author: amandeep-sg
GitHub stars: 3
Downloads: 365
Categories: Automation, Web Scraping

- Humanised error handling for LLM reconfiguration
- Comprehensive element interaction with visibility checks
- Full navigation control: open URLs, forward, backward, refresh
- Supports creating and quitting browser sessions
- Manages cookies (add, delete, get, clear)
- Performs clicks (left, right, double, drag‑and‑drop)
- Scrolls and resizes browser windows

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Selenium Mcp

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

From the repository

Clone the repository, create a Python virtual environment, install dependencies from requirements.txt, then run python server.py. Optionally set a Google GenAI API key in a .env file as GEMINI_API_KEY and use the built-in lightweight MCP client for testing.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "selenium mcp": {
            "selenium_mcp": {
                "command": "python3",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

McpServers

{
    "selenium_mcp": {
        "command": "python3",
        "args": [
            "-m",
            "venv",
            "venv"
        ]
    }
}

Introduction

This server is implemented in python to bridge the gap between the AI Assistant or (custom MCP clients) and Selenium Webdrivers. It exposes selenium webdriver functionalities as MCP tools allowing AI assistanct/MCP clients to user them to perform task for web automation, web testing or web scraping.

Release Notes

Version 2.0.1 - Release 11 April 2026

In this version, minor enhancements are made in error code, return types and readme file 1. Retun type changes from Union[None, dict], int, bool to str in 1. cookies.py 2. find.py 3. get.py 4. input.py

Version 2.0.0 - Release 4 April 2026

In this version, we have done some structural changes like seperating functions into save and get. Now save is just focused on saving files on the disk. And get is where LLM wants to get the data from the browser.

Following are the list of enhancements:
1. Get: To get webpage as markdown, html, screenshot, element's screenshot, list of urls
2. JS Executor: To execute javascript code for interacting with the webpage
3. Files: To upload and download files
4. Alerts: To handle alerts
5. Click: Added drag and drop of elements by xpath
6. File: To save webpage as pdf on disk

Version 1.0.0 - Release 31 March 2026

1. Web Driver: Create new or quit exiting webdiver sessions 2. Cookies: To manage cookies (add, delete, get, clear) 3. Clicks: To perform clicks on elements (left client, right click, double click) 4. Browser: To navigate urls and manage browser capabilities like resize, maximize, minimize, fullscreen, etc. 5. Scroll: To scroll the entire webpage 6. Input: Input text into elements and select/unselect checkbox, radio buttons, dropdowns options, etc. 7. Find: To find element by xPaths

Key Features

1. Humanised error handleing, enables LLM to intreperate errors and reconfigure tool usage accordingly 2. Comprehensive element interaction: Clicks, input, select are performed by checking if element is visible, enabled, clickable, etc 3. Full Navigation control: Open New url, click forward, backward, refresh, etc

The tools leverages following technologies to support
1. FastMCP: For MCP server implementation
2. Selenium: For web automation
3. Google GenAI: For AI assistant

Upcomming

Following are the list of features that will be added in the future: 1. Tools to support Chrome Dev Tools & BiDi 2. Enhance save functionality to save files in different formats 3. Enhanced error handling 4. Multi browser support (Firefox, Edge, Safari, etc)

Example

Prompt: "Open https://rfpnotification.com and join the waiting list by entering the email address: [test_user@example.com]"

|Before|After|
|------|-----|
| Before | After |

After running the script, the browser took the screenshot to check if the email was entered successfully.

Test In Action

Dev Setup

Clone the repository

git clone {url}

Create virtual environment

python3 -m venv venv

source venv/bin/activate

Install dependencies

pip install -r requirements.txt

Run the server

python server.py

The package comes with a lightweight MCP client using Google GenAI SDK to test the server. It is implemented in server.py file. To use it, you need to have a Google GenAI API key. Set it in the .env file as GEMINI_API_KEY={your_api_key}.

Run the client

python server.py

Architecture

The mcp has a very somple architecture as shown below. If this MCP is hosted locally then it communicates via stdio, if it is hosted on cloud then it communicates via http.

Architecture

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Introduction

Release Notes

Version 2.0.1 - Release 11 April 2026

Version 2.0.0 - Release 4 April 2026

Version 1.0.0 - Release 31 March 2026

Key Features

Upcomming

Example

Test In Action

Dev Setup

Architecture

Install

More like this

@mendableai/firecrawl Mcp Server

Umut Naci

Playwright

Fetch

Puppeteer

Playwright